Real-time Detection Transformer (RT-DETR) of Ornamental Fish Diseases with YOLOv9 using CNN (Convolutional Neural Network) Algorithm

Dwi Nurul Huda; Mochammad Rizki Romdoni; Liza Safitri; Ade Winarni; Abdur Rahman

doi:10.30871/jaic.v8i2.8561

Dwi Nurul Huda Sekolah Tinggi Teknologi Indonesia Tanjung Pinang
Mochammad Rizki Romdoni Sekolah Tinggi Teknologi Indonesia Tanjung Pinang
Liza Safitri Sekolah Tinggi Teknologi Indonesia Tanjung Pinang
Ade Winarni Sekolah Tinggi Teknologi Indonesia Tanjung Pinang
Abdur Rahman Sekolah Tinggi Teknologi Indonesia Tanjung Pinang

DOI: https://doi.org/10.30871/jaic.v8i2.8561

Keywords: CNN, Disease Detection, Real-time Detection Transformer (RT-DETR), Soft Voting Ensemble Learning, YOLOv9

Abstract

The lack of specialized tools to check the condition of ornamental fish has hindered effective management. This research proposes a novel software architecture that uses the YOLOv9 model combined with RT-DETR to enable accurate and timely identification of ornamental fish conditions including fish diseases, empowering farmers and hobbyists with a valuable resource. This integration is done using Soft Voting Ensemble Learning technique. To achieve this goal, an Android mobile application successfully classified healthy fish and accurately identified common diseases such as bacteria, fungal, parasitic, and whitetail. Based on the test results, the integration accuracy of the YOLOv9 and RT-DETR models produced a high result of 0.8947 while the stand-alone YOLOv9 showed 0.8889 and the stand-alone RT-DETR of 0.8904. Recommendations are given for the combination of YOLOv9 and RT-DETR in condition detection and diagnosis of ornamental fish diseases.

Downloads

Download data is not yet available.

References

E. Setiawan, R. F. Suwarman, A. Firmansyah, and M. D. Saputra, ‘Pelatihan Budidaya Dan Pemasaran Ikan Cupang Hias Untuk Mengatasi Masalah Ekonomi Di Masa Pandemi’, J. Abdimas Sang Buana, vol. 2, no. 1, p. 20, 2021, doi: 10.32897/abdimasusb.v2i1.511.

RRI, ‘Indonesia Negara Kedua Pengekspor Ikan Hias Terbesar’. [Online]. Available: https://www.rri.co.id/bisnis/418692/indonesia-negara-kedua-pengekspor-ikan-hias-terbesar

Administrator, ‘Buah Manis Kebijakan Ekonomi Biru’. [Online]. Available: https://indonesia.go.id/kategori/editorial/7752/buah-manis-kebijakan-ekonomi-biru?lang=1#:~:text=Semester I-2023 nilai ekspor,menggeser posisi Singapura dan Belanda.

Z. Wang, H. Liu, G. Zhang, X. Yang, L. Wen, and W. Zhao, ‘Diseased Fish Detection in the Underwater Environment Using an Improved YOLOV5 Network for Intensive Aquaculture’, Fishes, vol. 8, no. 3, 2023, doi: 10.3390/fishes8030169.

E. Li, Q. Wang, J. Zhang, W. Zhang, H. Mo, and Y. Wu, ‘Fish Detection under Occlusion Using Modified You Only Look Once v8 Integrating Real-Time Detection Transformer Features’, Appl. Sci. Switz., vol. 13, no. 23, 2023, doi: 10.3390/app132312645.

Y. Zhao et al., ‘DETRs Beat YOLOs on Real-time Object Detection’, 2023.

Z. Xing, J. Ren, X. Fan, and Y. Zhang, ‘S-DETR: A Transformer Model for Real-Time Detection of Marine Ships’, J. Mar. Sci. Eng., vol. 11, no. 4, 2023, doi: 10.3390/jmse11040696.

Z. Zhao, ‘Abnormal Behavior Fish and Population Detection Method based on Deep Learning’, vol. 4, no. 3, pp. 2–6, 2023.

R. Mahendran and G. P. Seneviratne, ‘Using CNN to Identify the Condition of Edible Fish’, 7th Int. Conf. Inf. Technol. Res. Digit. Resil. Reinvention ICITR 2022 - Proc., no. December 2022, 2022, doi: 10.1109/ICITR57877.2022.9993419.

S. Dash, S. Ojha, R. K. Muduli, S. P. Patra, and R. C. Barik, ‘Fish Type and Disease Classification Using Deep Learning Model Based Customized CNN with Resnet 50 Technique’, J. Adv. Zool., Mar. 2024, doi: 10.53555/jaz.v45i3.4194.

H. M. Zayani et al., ‘International Journal of INTELLIGENT SYSTEMS AND APPLICATIONS IN ENGINEERING Unveiling the Potential of YOLOv9 through Comparison with YOLOv8’, Orig. Res. Pap. Int. J. Intell. Syst. Appl. Eng. IJISAE, vol. 2024, no. 3, pp. 2845–2854, 2024.

R. Sapkota et al., ‘Comprehensive Performance Evaluation of YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments’, vol. 2024, no. August, 2024, doi: 10.48550/arXiv.2407.12040.

S. Tang and W. Yan, ‘Utilizing RT-DETR Model for Fruit Calorie Estimation from Digital Images’, Inf. Switz., vol. 15, no. 8, 2024, doi: 10.3390/info15080469.

E. K. Sahin, ‘Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest’, SN Appl. Sci., vol. 2, no. 7, pp. 1–17, 2020, doi: 10.1007/s42452-020-3060-1.

T. Aravanis, I. Hatzilygeroudis, and G. Spiliopoulos, ‘Ensemble Modelling for Predicting Fish Mortality †’, Appl. Sci. Switz., vol. 14, no. 15, pp. 1–16, 2024, doi: 10.3390/app14156540.

T. Fawcett, ‘An introduction to ROC analysis’, Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, 2006, doi: 10.1016/j.patrec.2005.10.010.

A. B. Prakosa, Hendry, and R. Tanone, ‘Implementasi Model Deep Learning Convolutional Neural Network (CNN) Pada Citra Penyakit Daun Jagung Untuk Klasifikasi Penyakit Tanaman’, J. Pendidik. Teknol. Inf. JUKANTI, vol. 6, no. 1, pp. 107–116, 2023.

O. B. Elhalid and A. H. Işık, ‘Enhancing Mobile Acute Lymphoblastic Cancer Detection: Transfer Learning from YOLOv9 to TensorFlow for Real-Time Applications’, Int. J. Pioneer. Technol. Eng., vol. 3, no. 01, pp. 21–26, 2024, doi: 10.56158/jpte.2024.70.3.01.

S. A. Hicks et al., ‘On evaluation metrics for medical applications of artificial intelligence’, Sci. Rep., vol. 12, no. 1, pp. 1–9, 2022, doi: 10.1038/s41598-022-09954-8.

M. Sokolova, N. Japkowicz, and S. Szpakowicz, ‘Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation’, AAAI Workshop - Tech. Rep., vol. WS-06-06, no. January, pp. 24–29, 2006, doi: 10.1007/11941439_114.